How real projects summarise themselves for language models.
runxhqllms.txtrunxhq/runx/llms.txt
docs/skill-author-runtime-contract.md) - [Skill Catalog](docs/skill-catalog.md) - [Security Authority Proof](docs/security-authority-proof.md) - [Rust Kernel Architecture](docs/rust-kernel-architecture.md) - [How We Test](docs/how-we-test.md) ## Examples - [Hello World](examples/hello-world) - [OpenAPI Tool](examples/openapi-tool) - [OpenAPI Graph](examples/openapi-graph) - [GitHub MCP Hero](examples/github-mcp-hero
zapierllms.txtzapier/wade-skills/llms.txt
Council](https://github.com/zapier/wade-skills/blob/main/skills/war-council/SKILL.md): Convenes a panel of opinionated expert personas to stress-test a decision and return a ranked, bet-weighted recommendation. - [Meeting Follow-Up Pipeline](https://github.com/zapier/wade-skills/blob/main/skills/meeting-follow-up-pipeline/SKILL.md):
AgriciDanielllms.txtAgriciDaniel/flow/llms-full.txt
# FLOW SEO Full Context --- title: "Start Here" description: "Start Here" updated: 2026-04-25
AgriciDanielllms.txtAgriciDaniel/flow/llms.txt
want the model to separate observations, assumptions, recommended actions, and claims tha... - [AI detector test follow-up Prompt](docs/09-prompts/optimize/ai-detector-test-follow-up-prompt.md): Use this prompt when you need a structured optimize deliverable
ChanMeng666llms.txtChanMeng666/echook/llms.txt
Codex CLI. An AI agent (Claude Code / Cursor / Codex) clones, installs, configures, tests, and uninstalls the whole project on the user's behalf — there are no human-interactive menus
guardanallms.txtguardana/guardana/site/llms.txt
rules - [writing-rules.md](https://raw.githubusercontent.com/guardana/guardana/refs/heads/main/docs/writing-rules.md): create YAML or Python rules - [usage-rule-test.md](https://raw.githubusercontent.com/guardana/guardana/refs/heads/main/docs/usage-rule-test.md): test positive, negative, and inconclusive fixtures - [extending.md](https://raw.githubusercontent.com/guardana/guardana/refs/heads/main/docs/extending.md): provide rules, evaluators, targets, or taxonomies
jangtrinhllms.txtjangtrinh/design-os-3d-blender/docs/llms.txt
keyboard delivery package with CAD proof. - [GitHub Repository](https://github.com/jangtrinh/design-os-3d-blender): Python automation scripts, test suites, and Blender runner
existential-birdsllms.txtexistential-birds/beagle/llms.txt
Beagle > Beagle is an Agent Skills marketplace: framework-aware code review, documentation, testing, architectural analysis, and git workflows for any compatible coding agent. It ships 10 plugins and 130+ skills
G12789llms.txtG12789/mcp-quickstart/llms.txt
command. TypeScript or Python, with example tool/resource/prompt, MCP Inspector wiring, and passing unit tests included. It can also generate MCP tools directly from an existing API — a whole OpenAPI spec
krzkollms.txtkrzko/google-cloud-mcp/llms-full.txt
server using Server-Sent Events (SSE). It is a standalone Apify Actor designed for testing MCP servers over SSE, with support for Authorization headers. It uses plain JavaScript (old-school
keep-starknet-strangellms.txtkeep-starknet-strange/starknet-agentic/llms.txt
starknet-agentic skills > Cairo/Starknet skills for AI coding agents — audit workflow, contract authoring, testing, optimization, deployment, and protocol constraints. ## Skills - [cairo-auditor](skills/cairo-auditor/SKILL.md): Security review with parallel vector specialists
AuthPlanellms.txtAuthPlane/authserver/llms.txt
Broker / federation flows. - [Compliance matrix](docs/reference/compliance.md): RFC-by-RFC support. - [MCP client compatibility](docs/reference/mcp-client-compatibility.md): tested clients. ## Concepts (mental model) - [What is Authplane?](docs/concepts/what-is-authplane.md): 60-second overview. - [Resources and scopes](docs/concepts/resources-and-scopes.md
shiqudallms.txtshiquda/roadmap-skill/llms-full.txt
component boundaries - docs/tool-interface-standard.md: public MCP tool rules and output conventions - AGENTS.md: development conventions, testing, and release workflow - CHANGELOG.md: product evolution and release history Canonical URLs: - GitHub repository: https://github.com/shiquda/roadmap-skill
shiqudallms.txtshiquda/roadmap-skill/llms.txt
invocation rules, input conventions, and output contracts - [AGENTS.md](https://raw.githubusercontent.com/shiquda/roadmap-skill/main/AGENTS.md): Development conventions, commands, testing, and release workflow - [CHANGELOG.md](https://raw.githubusercontent.com/shiquda/roadmap-skill/main/CHANGELOG.md): Version history and recent changes ## Important Facts - local
sandraschillms.txtsandraschi/inkscape-mcp/llms.txt
PORT`; MCP path default `/mcp` | ## Packaging - **uv** + `pyproject.toml` — [docs/INSTALL.md](docs/INSTALL.md) - **justfile** — `just test`, `just mcpb-pack`, etc. - **MCPB** — `just mcpb-pack` → `dist/inkscape-mcp-v*.mcpb` (see [docs/MCPB.md](docs/MCPB.md)) ## Maintainer / upstream Repository
AsiaOstrichllms.txtAsiaOstrich/universal-dev-standards/llms.txt
Acceptance Criteria Traceability Standards](https://github.com/AsiaOstrich/universal-dev-standards/blob/main/core/acceptance-criteria-traceability.md): `acceptance-criteria-traceability`, level 3 - [Acceptance Test-Driven Development (ATDD) Standards](https://github.com/AsiaOstrich/universal-dev-standards/blob/main/core/acceptance-test-driven-development.md): `acceptance-test-driven-development`, level 3 - [Accessibility Standards
HuckleR2003llms.txtHuckleR2003/PC_Workman_HCK/docs/llms-full.txt
definitions. - 340 offline hardware-compatibility entries: 196 CPUs, 84 GPUs and 60 chipsets. - 330 tests in the current source suite. - Five workload-learning buckets: idle, light, medium, heavy and gaming
HuckleR2003llms.txtHuckleR2003/PC_Workman_HCK/docs/llms.txt
August after 29 days; 474 commits and 1,418 EditMode plus 65 PlayMode tests after 48 days; built by one person in the evenings after ten to twelve hour taxi
digital-go-jpllms.txtdigital-go-jp/administrative-procedures-mcp/llms.txt
work with the Japanese data in English - [Development guide (English)](docs/development.en.md): architecture, trust boundary, tests, adding datasets - [dataset.yaml guide (English)](docs/dataset-yaml-guide.en.md): the dataset definition format (field roles, codelist, notes, computed
Scottcjnllms.txtScottcjn/shaprai/llms.txt
Quality Write code that humans can read and maintain. Include type hints and docstrings. Test your changes. Follow existing project style. Small focused changes beat large rewrites. 3. Communication
A markdown file at a website's root that gives language models a short guide to the site and links to the pages worth reading.
The same idea with the content included, so an agent can read the documentation in one request.
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.
